Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models Article Swipe
Haipeng Wang
,
Zhengyuan Wei
,
Qilin Zhou
,
W. K. Chan
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.12428
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.12428
In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL) models, many state-of-the-art robustness-oriented fuzzing techniques are metric-oriented. The pipeline generates adversarial examples as test cases via such a DL testing technique and retrains the DL model under test with test suites that contain these test cases. On the one hand, the strategies of these fuzzing techniques tightly integrate the key characteristics of their testing metrics. On the other hand, they are often unaware of whether their generated test cases are different from the samples surrounding these test cases and whether there are relevant test cases of other seeds when generating the current one. We propose a novel testing metric called Contextual Confidence (CC). CC measures a test case through the surrounding samples of a test case in terms of their mean probability predicted to the prediction label of the test case. Based on this metric, we further propose a novel fuzzing technique Clover as a DL testing technique for the pipeline. In each fuzzing round, Clover first finds a set of seeds whose labels are the same as the label of the seed under fuzzing. At the same time, it locates the corresponding test case that achieves the highest CC values among the existing test cases of each seed in this set of seeds and shares the same prediction label as the existing test case of the seed under fuzzing that achieves the highest CC value. Clover computes the piece of difference between each such pair of a seed and a test case. It incrementally applies these pieces of differences to perturb the current test case of the seed under fuzzing that achieves the highest CC value and to perturb the resulting samples along the gradient to generate new test cases for the seed under fuzzing.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2407.12428
- https://arxiv.org/pdf/2407.12428
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403749844
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403749844Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2407.12428Digital Object Identifier
- Title
-
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-07-17Full publication date if available
- Authors
-
Haipeng Wang, Zhengyuan Wei, Qilin Zhou, W. K. ChanList of authors in order
- Landing page
-
https://arxiv.org/abs/2407.12428Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2407.12428Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2407.12428Direct OA link when available
- Concepts
-
Fuzz testing, Robustness (evolution), Computer science, Artificial intelligence, Context (archaeology), Machine learning, Geography, Programming language, Software, Gene, Biochemistry, Archaeology, ChemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403749844 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2407.12428 |
| ids.doi | https://doi.org/10.48550/arxiv.2407.12428 |
| ids.openalex | https://openalex.org/W4403749844 |
| fwci | |
| type | preprint |
| title | Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9323999881744385 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C111065885 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8659266233444214 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1189053 |
| concepts[0].display_name | Fuzz testing |
| concepts[1].id | https://openalex.org/C63479239 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7288657426834106 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[1].display_name | Robustness (evolution) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6243507862091064 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5040134787559509 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C2779343474 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4594389796257019 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[4].display_name | Context (archaeology) |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3724537193775177 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C205649164 |
| concepts[6].level | 0 |
| concepts[6].score | 0.09318217635154724 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[6].display_name | Geography |
| concepts[7].id | https://openalex.org/C199360897 |
| concepts[7].level | 1 |
| concepts[7].score | 0.051410794258117676 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[7].display_name | Programming language |
| concepts[8].id | https://openalex.org/C2777904410 |
| concepts[8].level | 2 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7397 |
| concepts[8].display_name | Software |
| concepts[9].id | https://openalex.org/C104317684 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[9].display_name | Gene |
| concepts[10].id | https://openalex.org/C55493867 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[10].display_name | Biochemistry |
| concepts[11].id | https://openalex.org/C166957645 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[11].display_name | Archaeology |
| concepts[12].id | https://openalex.org/C185592680 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[12].display_name | Chemistry |
| keywords[0].id | https://openalex.org/keywords/fuzz-testing |
| keywords[0].score | 0.8659266233444214 |
| keywords[0].display_name | Fuzz testing |
| keywords[1].id | https://openalex.org/keywords/robustness |
| keywords[1].score | 0.7288657426834106 |
| keywords[1].display_name | Robustness (evolution) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6243507862091064 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5040134787559509 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/context |
| keywords[4].score | 0.4594389796257019 |
| keywords[4].display_name | Context (archaeology) |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.3724537193775177 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/geography |
| keywords[6].score | 0.09318217635154724 |
| keywords[6].display_name | Geography |
| keywords[7].id | https://openalex.org/keywords/programming-language |
| keywords[7].score | 0.051410794258117676 |
| keywords[7].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2407.12428 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2407.12428 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2407.12428 |
| locations[1].id | doi:10.48550/arxiv.2407.12428 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2407.12428 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100405759 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-7410-393X |
| authorships[0].author.display_name | Haipeng Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Haipeng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5072631246 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5966-1338 |
| authorships[1].author.display_name | Zhengyuan Wei |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wei, Zhengyuan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5103178922 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2289-9849 |
| authorships[2].author.display_name | Qilin Zhou |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhou, Qilin |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5020936420 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-7726-6235 |
| authorships[3].author.display_name | W. K. Chan |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Chan, Wing-Kwong |
| authorships[3].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2407.12428 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9323999881744385 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Anomaly Detection Techniques and Applications |
| related_works | https://openalex.org/W3072699177, https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W3107602296, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W4364306694, https://openalex.org/W4312192474 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2407.12428 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2407.12428 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2407.12428 |
| primary_location.id | pmh:oai:arXiv.org:2407.12428 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2407.12428 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2407.12428 |
| publication_date | 2024-07-17 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 31, 109, 119, 127, 152, 158, 172, 251, 254 |
| abstract_inverted_index.At | 189 |
| abstract_inverted_index.CC | 117, 203, 238, 279 |
| abstract_inverted_index.DL | 32, 38, 159 |
| abstract_inverted_index.In | 0, 165 |
| abstract_inverted_index.It | 257 |
| abstract_inverted_index.On | 50, 69 |
| abstract_inverted_index.We | 107 |
| abstract_inverted_index.as | 26, 157, 181, 224 |
| abstract_inverted_index.in | 130, 213 |
| abstract_inverted_index.it | 193 |
| abstract_inverted_index.of | 9, 56, 65, 77, 99, 126, 132, 141, 174, 184, 210, 216, 229, 244, 250, 262, 270 |
| abstract_inverted_index.on | 146 |
| abstract_inverted_index.to | 137, 264, 282, 290 |
| abstract_inverted_index.we | 149 |
| abstract_inverted_index.The | 21 |
| abstract_inverted_index.and | 35, 92, 218, 253, 281 |
| abstract_inverted_index.are | 19, 74, 83, 95, 178 |
| abstract_inverted_index.for | 4, 162, 295 |
| abstract_inverted_index.key | 63 |
| abstract_inverted_index.new | 292 |
| abstract_inverted_index.one | 52 |
| abstract_inverted_index.set | 173, 215 |
| abstract_inverted_index.the | 1, 6, 37, 51, 54, 62, 70, 86, 104, 123, 138, 142, 163, 179, 182, 185, 190, 195, 201, 206, 220, 225, 230, 236, 242, 266, 271, 277, 284, 288, 296 |
| abstract_inverted_index.via | 29 |
| abstract_inverted_index.(DL) | 12 |
| abstract_inverted_index.case | 121, 129, 198, 228, 269 |
| abstract_inverted_index.deep | 10 |
| abstract_inverted_index.each | 166, 211, 247 |
| abstract_inverted_index.from | 85 |
| abstract_inverted_index.many | 14 |
| abstract_inverted_index.mean | 134 |
| abstract_inverted_index.one. | 106 |
| abstract_inverted_index.pair | 249 |
| abstract_inverted_index.same | 180, 191, 221 |
| abstract_inverted_index.seed | 186, 212, 231, 252, 272, 297 |
| abstract_inverted_index.such | 30, 248 |
| abstract_inverted_index.test | 27, 41, 43, 48, 81, 90, 97, 120, 128, 143, 197, 208, 227, 255, 268, 293 |
| abstract_inverted_index.that | 45, 199, 234, 275 |
| abstract_inverted_index.they | 73 |
| abstract_inverted_index.this | 147, 214 |
| abstract_inverted_index.when | 102 |
| abstract_inverted_index.with | 42 |
| abstract_inverted_index.(CC). | 116 |
| abstract_inverted_index.Based | 145 |
| abstract_inverted_index.along | 287 |
| abstract_inverted_index.among | 205 |
| abstract_inverted_index.case. | 144, 256 |
| abstract_inverted_index.cases | 28, 82, 91, 98, 209, 294 |
| abstract_inverted_index.finds | 171 |
| abstract_inverted_index.first | 170 |
| abstract_inverted_index.hand, | 53, 72 |
| abstract_inverted_index.label | 140, 183, 223 |
| abstract_inverted_index.model | 39 |
| abstract_inverted_index.novel | 110, 153 |
| abstract_inverted_index.often | 75 |
| abstract_inverted_index.other | 71, 100 |
| abstract_inverted_index.piece | 243 |
| abstract_inverted_index.seeds | 101, 175, 217 |
| abstract_inverted_index.terms | 131 |
| abstract_inverted_index.their | 66, 79, 133 |
| abstract_inverted_index.there | 94 |
| abstract_inverted_index.these | 47, 57, 89, 260 |
| abstract_inverted_index.time, | 192 |
| abstract_inverted_index.under | 40, 187, 232, 273, 298 |
| abstract_inverted_index.value | 280 |
| abstract_inverted_index.whose | 176 |
| abstract_inverted_index.Clover | 156, 169, 240 |
| abstract_inverted_index.called | 113 |
| abstract_inverted_index.cases. | 49 |
| abstract_inverted_index.labels | 177 |
| abstract_inverted_index.metric | 112 |
| abstract_inverted_index.pieces | 261 |
| abstract_inverted_index.round, | 168 |
| abstract_inverted_index.shares | 219 |
| abstract_inverted_index.suites | 44 |
| abstract_inverted_index.value. | 239 |
| abstract_inverted_index.values | 204 |
| abstract_inverted_index.applies | 259 |
| abstract_inverted_index.between | 246 |
| abstract_inverted_index.contain | 46 |
| abstract_inverted_index.current | 105, 267 |
| abstract_inverted_index.further | 150 |
| abstract_inverted_index.fuzzing | 17, 58, 154, 167, 233, 274 |
| abstract_inverted_index.highest | 202, 237, 278 |
| abstract_inverted_index.locates | 194 |
| abstract_inverted_index.metric, | 148 |
| abstract_inverted_index.models, | 13 |
| abstract_inverted_index.perturb | 265, 283 |
| abstract_inverted_index.propose | 108, 151 |
| abstract_inverted_index.samples | 87, 125, 286 |
| abstract_inverted_index.testing | 33, 67, 111, 160 |
| abstract_inverted_index.through | 122 |
| abstract_inverted_index.tightly | 60 |
| abstract_inverted_index.unaware | 76 |
| abstract_inverted_index.whether | 78, 93 |
| abstract_inverted_index.achieves | 200, 235, 276 |
| abstract_inverted_index.computes | 241 |
| abstract_inverted_index.examples | 25 |
| abstract_inverted_index.existing | 207, 226 |
| abstract_inverted_index.fuzzing. | 188, 299 |
| abstract_inverted_index.generate | 291 |
| abstract_inverted_index.gradient | 289 |
| abstract_inverted_index.learning | 11 |
| abstract_inverted_index.measures | 118 |
| abstract_inverted_index.metrics. | 68 |
| abstract_inverted_index.pipeline | 3, 22 |
| abstract_inverted_index.property | 8 |
| abstract_inverted_index.relevant | 96 |
| abstract_inverted_index.retrains | 36 |
| abstract_inverted_index.different | 84 |
| abstract_inverted_index.enhancing | 5 |
| abstract_inverted_index.generated | 80 |
| abstract_inverted_index.generates | 23 |
| abstract_inverted_index.integrate | 61 |
| abstract_inverted_index.pipeline. | 164 |
| abstract_inverted_index.predicted | 136 |
| abstract_inverted_index.resulting | 285 |
| abstract_inverted_index.technique | 34, 155, 161 |
| abstract_inverted_index.Confidence | 115 |
| abstract_inverted_index.Contextual | 114 |
| abstract_inverted_index.difference | 245 |
| abstract_inverted_index.generating | 103 |
| abstract_inverted_index.prediction | 139, 222 |
| abstract_inverted_index.robustness | 7 |
| abstract_inverted_index.strategies | 55 |
| abstract_inverted_index.techniques | 18, 59 |
| abstract_inverted_index.adversarial | 24 |
| abstract_inverted_index.differences | 263 |
| abstract_inverted_index.probability | 135 |
| abstract_inverted_index.surrounding | 88, 124 |
| abstract_inverted_index.corresponding | 196 |
| abstract_inverted_index.incrementally | 258 |
| abstract_inverted_index.characteristics | 64 |
| abstract_inverted_index.metric-oriented. | 20 |
| abstract_inverted_index.state-of-the-art | 15 |
| abstract_inverted_index.testing-retraining | 2 |
| abstract_inverted_index.robustness-oriented | 16 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |